Gautam Kamath
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP synthesis methods generally fail to achieve this capability gain.
The paper introduces ContinuousBench, a dynamic benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge and capabilities from sensitive source corpora, finding that current state-of-the-art DP methods generally fail to achieve this.
The paper establishes tight upper and lower bounds on the statistical cost of approximate machine unlearning for smooth strongly convex losses, showing that the optimal unlearning rate depends critically on the relationship between the unlearning parameter $\varepsilon$ and the model dimension $d$.
The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are invisible when analyzing individual stages.
Papers
Sequential Data Poisoning in LLM Post-Training
Jack Sanderson, Yihan Wang, Xiaoqian Lu, Gautam Kamath +1 more
The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are in…